Risk Aversion Operator for Addressing Maximization Bias in Q-Learning.

Bi Wang Xuelian Li Zhiqiang Gao Yangjun Zhong

Published in: IEEE Access (2020)

Keyphrases

risk aversion
utility function
risk averse
risk neutral
expected utility
reinforcement learning
state space
cooperative
multi agent
optimal policy
inventory level
learning algorithm
objective function
model free
exchange rate
dynamic programming
decision theory
decision problems